Uncensored AI API Quickstart Guide

Base URL and Authentication

To use the uncensored ai api, point your client to the base URL: https://api.uncensoredai.top/v1. This endpoint is compatible with official OpenAI SDKs and any OpenAI-compatible client. You only need a single API key, which you generate instantly on the Get API key page via Google or email. The key is displayed once after creation; store it securely in your environment variables.

• Authentication is handled via the Authorization: Bearer <your-api-key> header.
• Only one active key is allowed per account; generating a new key replaces the previous one.
• No phone number is required for signup, and no card is needed for the initial trial.

Copycurl https://api.uncensoredai.top/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

The /v1/chat/completions Endpoint

Send your prompts to the POST /v1/chat/completions endpoint. The model identifier is simply uncensored. This endpoint accepts standard chat messages and returns text completions. It does not support embeddings, images, audio, or video generation. If you need those features, you must handle them separately.

• Use the model field set to uncensored in your request body.
• The uncensored llm api supports function calling (tools), JSON mode, and standard parameters like temperature and top_p.
• All requests are processed against a single, dedicated model tuned for minimal content refusal.

Request Parameters: Temperature and Top P

Control the model's output style using standard LLM parameters. Set temperature to adjust randomness (lower values are more deterministic, higher values are more creative). Use top_p for nucleus sampling to control vocabulary diversity. Other available parameters include stop, seed, presence_penalty, and frequency_penalty.

• These parameters allow fine-tuning of the uncensored ai models api output for your specific use case.
• JSON mode can be enabled via response_format: {"type": "json_object"} for structured data.
• Function calling is supported via the tools parameter for agent-like behavior.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.uncensoredai.top/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Response Format: Streaming and JSON

Enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE). Token usage statistics are included only in the final chunk of the stream. For structured outputs, use JSON mode to ensure the response is valid JSON, which is useful for parsing data programmatically.

• Streaming reduces perceived latency by delivering tokens as they are generated.
• The uncensored api ensures that all lawful adult, fictional, or controversial topics are processed without standard refusals.
• Always handle the final chunk to retrieve usage data for billing.

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Model Details and Limits

The uncensored model runs on our dedicated servers with a 64,000 token context window (prompt + completion combined). The maximum output per request is 16,000 tokens, or 2,048 tokens if max_tokens is not specified. Request bodies are limited to 8 MB. You are allowed 300 requests per minute and 8 concurrent requests per key.

• A hard content limit applies: sexual content involving minors is always refused.
• Errors and refusals do not consume your prepaid credit.
• The uncensored ai api is a text-only service; no embeddings or vision models are available.

SDK Examples and Error Handling

Use the official OpenAI SDKs or any compatible client. For Node.js, install the openai package and configure the base URL. Common errors include 401 for invalid keys, 402 if prepaid credit is exhausted, and 429 for rate limits. Credit is charged by real token usage, and prepaid credit never expires.

• Top-ups are crypto-only (USDT TRC20 or USDC Base) from $10 to $500.
• New accounts receive $0.50 in trial credit valid for 7 days.
• No card is needed for the trial, and no monthly fees apply.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.uncensoredai.top/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);